Spoken Word Recognition Using Slantlet Transform and Dynamic Time Warping

  • Sadiq J. Abou-Loukh University of Baghdad, College of Engineering, Electrical Eng. Dept
  • Samah Mutasher Gatea University of Baghdad, College of Engineering, Electrical Eng. Dept
Keywords: Speech Signal Recognition, Slantlet Transform, Dynamic Time Warping,, Discrete Wavelet Transform.

Abstract

Speech recognition system has been widely used by many researchers using different methods to fulfill a fast and accurate system. Speech signal recognition is a typical classification problem, which generally includes two main parts: feature extraction and classification. In this work, three feature extraction methods, namely SLT, DWT Db1 and DWT Db4, were compared. The dynamic time warping (DTW) algorithm is used for recognition. Twenty three Arabic words were

recorded fifteen different times in a studio by one speaker to form a database. The proposed system was evaluated using this database. The result shows recognition accuracy of 93.04%, 92.17% and 94.78% using DWT Db1, DWT Db4 and SLT respectively.

Published
2011-03-26
How to Cite
Abou-Loukh, S., & Gatea, S. (2011). Spoken Word Recognition Using Slantlet Transform and Dynamic Time Warping. Al-Nahrain Journal for Engineering Sciences, 14(1), 34-45. Retrieved from https://nahje.com/index.php/main/article/view/600